Skip to Main content Skip to Navigation
Master thesis

Implémentation et évaluation d’algorithmes parallèles de FFTs 3D à base de modèles de composants logiciels

Jérôme Richard 1, 2
2 AVALON - Algorithms and Software Architectures for Distributed and HPC Platforms
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme
Abstract : The Fast Fourier Transform (FFT) is a widely-used building block for many high-performance scientific applications. Efficient computing of FFT is paramount for the performance of these applications. This has led to many efforts to implement machine and computation specific optimizations. However, no existing FFT library is capable of easily integrating and automating the selection of new and/or unique optimizations.To ease FFT specialization, this study evaluates the use of component-based software engineering, a programming paradigm which consists in building applications by assembling small software units. Component models are known to have many software engineering benefits but usually have insufficient performance for high-performance scientific applications.This talk uses the L²C model, a general purpose high-performance component model, and studies its performance and adaptation capabilities on 3D FFTs. Experiments show that L²C, and components in general, enables easy handling of 3D FFT specializations while obtaining performance comparable to that of well-known libraries.
Complete list of metadata

Cited literature [37 references]  Display  Hide  Download

https://hal.inria.fr/hal-01082575
Contributor : Jérôme Richard <>
Submitted on : Monday, November 17, 2014 - 10:53:01 AM
Last modification on : Monday, May 4, 2020 - 11:38:58 AM
Long-term archiving on: : Friday, April 14, 2017 - 1:02:29 PM

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

  • HAL Id : hal-01082575, version 1

Citation

Jérôme Richard. Implémentation et évaluation d’algorithmes parallèles de FFTs 3D à base de modèles de composants logiciels. Calcul parallèle, distribué et partagé [cs.DC]. 2014. ⟨hal-01082575⟩

Share

Metrics

Record views

446

Files downloads

1321